[1]董 胡,马振中,赵 娜,等.基于 MMSE-MLSA 与感知滤波的语音增强算法[J].计算机技术与发展,2019,29(08):67-70.[doi:10. 3969 / j. issn. 1673-629X. 2019. 08. 013]
　DONG Hu,MA Zhen-zhong,ZHAO Na,et al.Speech Enhancement Algorithm Based on MMSE- MLSA and Perceptual Filtering[J].,2019,29(08):67-70.[doi:10. 3969 / j. issn. 1673-629X. 2019. 08. 013]
点击复制

基于 MMSE-MLSA 与感知滤波的语音增强算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年08期
页码:
67-70
栏目:
智能、算法、系统工程
出版日期:
2019-08-10

文章信息/Info

Title:
Speech Enhancement Algorithm Based on MMSE- MLSA and Perceptual Filtering
文章编号:
1673-629X(2019)08-0067-04
作者:
董 胡; 马振中; 赵 娜; 刘 刚; 童 欣
长沙师范学院 信息科学与工程学院,湖南 长沙 410100
Author(s):
DONG Hu; MA Zhen-zhong; ZHAO Na; LIU Gang; TONG Xin
School of Information Science and Engineering,Changsha Normal University,Changsha 410100,China
关键词:
语音增强; 最小均方误差; 感知滤波; 掩蔽阈值; 谱估计
Keywords:
speech enhancement; minimum mean square error; perceptual filtering; masking threshold; spectral estimation
分类号:
TN912.3
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 08. 013
摘要:
在语音通信过程中,纯净的语音信号可能受到各种不同类型的干扰噪声信号的影响,例如白噪声、色噪声等。 针对常见语音增强算法在低信噪比的复杂噪声环境下语音增强后存在语音失真及残余噪声的问题,提出了一种结合改进对数谱幅度的最小均方误差(MMSE-MLSA)谱估计与感知滤波的语音增强算法。 该算法采用 MMSE-MLSA 对含噪语音作初级谱估计增强处理,使用次级感知滤波器进一步掩蔽初级增强信号中的残余音乐噪声。 仿真实验结果表明,在低信噪比的复杂噪声环境下,该算法能有效降低语音失真及去除残余音乐噪声,与另外两种语音增强算法比较,增强效果更加突出。
Abstract:
In the process of speech communication,pure speech signal may be affected by various types of interference noise signals,such as white noise,color noise,etc. In order to solve the problem of speech distortion and residual noise in speech enhancement algorithms under complex noise environment with low SNR,a speech enhancement algorithm based on minimum mean square error-modified log-spectral amplitude (MMSE-MLSA) spectrum estimation and perceptual filtering is proposed. The noisy speech is enhanced by MMSE-MLSA as primary spectrum estimation, then a secondary perceptual filter is used to mask the residual music noise after primary enhancement. The simulation shows that the proposed algorithm can effectively reduce speech distortion and remove residual music noise in complex noise environment with low SNR. Compared with the other two algorithms of speech enhancement,the enhancement effect of the method proposed is more prominent.

相似文献/References:

[1]丁伟 吴小培.基于改进谱减方法的语音增强研究[J].计算机技术与发展,2008,(09):98.
　DING Wei,WU Xiao-pei.Implementation of Speech Enhancement Based on Improved Spectral Subtraction[J].,2008,(08):98.
[2]汝振 李昕 陈飞 杨李箭 李翔.一种基于HHT的语音增强算法研究与仿真[J].计算机技术与发展,2010,(08):116.
　RU Zhen,LI Xin,CHEN Fei,et al.Research and Simulation of Speech Enhancement Algorithm Based on HHT[J].,2010,(08):116.
[3]周述畅 宋亚男 吴光波.基于麦克风阵列的语音增强研究[J].计算机技术与发展,2012,(07):204.
　ZHOU Shu-chang,SONG Ya-nan,WU Guang-bo.Speech Enhancement Research Based on Microphone Array[J].,2012,(08):204.
[4]陈欢,邱晓晖.改进谱减法语音增强算法的研究[J].计算机技术与发展,2014,24(04):69.
　CHEN Huan,QIU Xiao-hui.Research on Speech Enhancement of Improved Spectral Subtraction Algorithm[J].,2014,24(08):69.
[5]董胡. 低信噪比环境下改进的语音端点检测算法[J].计算机技术与发展,2016,26(03):71.
　DONG Hu. Improved Speech Endpoint Detection under Low SNR Environment[J].,2016,26(08):71.
[6]孙成立,王海武.生成式对抗网络在语音增强方面的研究[J].计算机技术与发展,2019,29(02):152.[doi:10．3969/j．issn．1673－629X．2019．02．032]
　SUN Chengli,WANG Haiwu.Research on Speech Enhancement of Generative Adversarial Networks[J].,2019,29(08):152.[doi:10．3969/j．issn．1673－629X．2019．02．032]
[7]詹 展,秦会斌.基于新阈值函数的小波阈值去噪算法[J].计算机技术与发展,2019,29(11):47.[doi:10. 3969 / j. issn. 1673-629X. 2019. 11. 010]
　ZHAN Zhan,QIN Hui-bin.A Wavelet Threshold Denoising Algorithm Based on New Threshold Function[J].,2019,29(08):47.[doi:10. 3969 / j. issn. 1673-629X. 2019. 11. 010]
[8]董 胡,徐雨明,马振中,等.基于小波包与自适应维纳滤波的语音增强算法[J].计算机技术与发展,2020,30(01):50.[doi:10. 3969 / j. issn. 1673-629X. 2020. 01. 009]
　DONG Hu,XU Yu-ming,MA Zhen-zhong,et al.Speech Enhancement Algorithm Based on Wavelet Packet and Adaptive Wiener Filter[J].,2020,30(08):50.[doi:10. 3969 / j. issn. 1673-629X. 2020. 01. 009]

更新日期/Last Update: 2019-08-10